MLINFO COLLECTION
日次更新の新着・公開記事を新しい順に掲載しています。
Good decisions often require considering how outcomes will feel. Yet large language models (LLMs) increasingly enter decision workflows, despite little being known about how they map outcomes to…
Large language models have been shown to memorise and reproduce verbatim sequences from their training data, raising concerns about privacy leakage, intellectual property exposure, and the limits of…
Recent diffusion-based methods have substantially advanced image editing, yet parametric 3D control at the part level remains challenging. Existing approaches either operate on whole objects with…
Holistic co-speech motion generation aims to synthesize coordinated facial expressions, hand gestures, and body movements from speech, which is challenging due to heterogeneous part-specific…
We present FieldGuideRAG, a training-free GraphRAG method in which a vision-language model, or VLM, recognizes fine-grained species by comparing the query with real photographs stored on the nodes of…
Generative audio systems can produce large libraries of personalized bedtime content, but ordinary media objectives (retention, completion, and novelty) are poorly aligned with the goal of supporting…
Conversational RAG benchmarks such as MTRAG and RETECO evaluate retrieval and generation end to end: each system answers from its own retrieval, so abstention must be scored against whether each…
Do contract terms that protect investment between people also protect it between profit-maximizing language-model agents? In the hold-up problem, a seller can adapt a unit to one buyer at a cost…
Recent progress in deep learning has substantially advanced automated grading of ophthalmologic pathologies, supported by large annotated datasets and improved representation learning. However, a…
Long-range detection of small drones is complicated by their visual similarity to birds and by the limited detail available from ground-based cameras. Combining visible and infrared observations…
Real-time 4D occupancy forecasting requires reliably extrapolating both ego motion and surrounding actor motion under strict latency budgets. Recent occupancy world models improve long-horizon…
The bottleneck of attention mechanisms, which are the fundamental building block of modern language models, is their quadratic complexity in terms of context size. There has thus been an increasing…
Recommendation systems that optimize for the average user can fail to capture the preferences of diverse demographic groups. We consider a dynamic recommendation system, where arriving users can…
Vision-centric autonomous driving models encode thousands of image tokens per frame, yet most depict sky, buildings, or empty road---content irrelevant to planning. Worse, these tokens dilute the…
Human preferences change over time: an established preference may remain valid over time, become uncertain as context shifts, or be explicitly revised. Effective personalization requires…
Test-time scaling (TTS) improves large language model agents by sampling and selecting among multiple candidate trajectories, but common realizations assume that these trajectories can be executed in…
Automated red teaming trains an attacker large language model (LLM) to elicit harmful responses from a victim LLM, but reinforcement learning can collapse attackers onto a narrow set of prompts when…
End-to-end policies, from task-specific controllers to robot foundation models, learn complex behavior from raw observations but are not guaranteed to remain safe, so they are often wrapped in a…
Autonomous delivery robots increasingly share residential spaces with companion animals, yet navigation behavior is rarely designed with animal welfare in mind. This paper presents a pilot study…
Training acceleration methods for diffusion transformers, such as REPA and dispersive regularization, are commonly explained by additional supervision, spatial-structure priors, or improved feature…
Vision-language agents equipped with tools expose intermediate outputs for inspection and comparison with the model's reasoning, which may offer safety benefits over single-shot models. This paper…
Histopathology foundation models learn rich embedding representations, but their internal structure remains difficult to inspect. Concept-level interpretability is particularly relevant in…
Flapping-wing simulation must reconcile high-frequency wingbeat aerodynamics with the slower dynamics relevant to flight control and reinforcement learning. We present FlapSim, a modular open-source…
Reliable visual perception is essential for safe autonomous underwater exploration. Yet vision models pretrained on terrestrial images become less reliable underwater, where turbidity, backscatter,…